AgentMind Python SDK
Python SDK for AgentMind, an infrastructure platform for autonomous AI agents.
Installation
Install locally
pip install agentmind-sdk
Basic Usage
from agentmind import AgentMindClient
client = AgentMindClient(
base_url="https://your-agentmind-api.up.railway.app",
api_key="agm_your_api_key"
)
response = client.chat(
task="What is 45 * 12?",
llm_config={
"provider": "openai",
"api_key": "your_openai_api_key",
"model": "gpt-4.1-mini"
}
)
print(response)
Register an Agent
from agentmind import AgentMindClient
client = AgentMindClient(
base_url="https://your-agentmind-api.up.railway.app"
)
result = client.register_agent(
name="Research Agent",
purpose="Testing AgentMind",
invite_code="AGENTMIND-BETA-001",
permissions=[
"memory:read",
"memory:write",
"tools:calculator:run",
"tools:echo:run",
"tools:quadratic_solver:run"
]
)
print(result["api_key"])
Save Memory
client.save_memory(
"This agent prefers short technical answers."
)
Search Memory
client.search_memory(
"answer style"
)
List Available Tools
client.list_tools()
Get Tool Details
client.get_tool("quadratic_solver")
Run Tool Directly
client.run_tool(
"calculator",
{
"expression": "45 * 12"
}
)
Runtime Chat
client.chat(
task="Solve x^2 - 5x + 6 = 0",
memory_search_limit=5,
save_result_to_memory=False
)
Features
- Agent authentication
- Memory storage
- Vector memory search
- Tool discovery
- Tool execution
- Autonomous runtime reasoning
- MCP-compatible architecture
- Structured validation
- Tool schema registry
- Railway deployment support
Architecture
Developer Agent
↓
AgentMind SDK
↓
AgentMind API
↓
Runtime + Memory + Tools
↓
PostgreSQL / Redis / ChromaDB
Error Handling
The SDK includes:
AgentMindErrorAgentMindAuthErrorAgentMindAPIError
Example:
from agentmind import (
AgentMindClient,
AgentMindAPIError
)
try:
client.chat("What is 45 * 12?")
except AgentMindAPIError as error:
print(error)
SDK Methods
| Method | Description |
|---|---|
get_manifest() |
Get platform manifest |
register_agent() |
Register new agent |
me() |
Get current agent |
save_memory() |
Save memory |
search_memory() |
Search memories |
list_tools() |
List all tools |
get_tool() |
Get one tool schema |
run_tool() |
Execute tool |
chat() |
Use autonomous runtime |
Local Testing
python test_sdk.py
Future Improvements
- Async SDK
- Streaming runtime responses
- Built-in retries
- Typed response models
- CLI support
- WebSocket support
- Hosted MCP integration
Author
Built by Olumba C Patrick
Metadata
Release files for agentmind-sdk 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentmind_sdk-0.1.1.tar.gz | 6.6 kB | With provenance | Details for agentmind_sdk-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentmind_sdk-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for agentmind_sdk-0.1.1-py3-none-any.whl |
Total release size: 14.0 kB
Release files / agentmind_sdk-0.1.1.tar.gz
| Download URL | agentmind_sdk-0.1.1.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
15db3c769cafb9ef86bb7e93114e3d568b380d94d7f6e27a319ba4e3f5f683cf
|
|
BLAKE2b-256 checksum How to use checksums |
a4becd2dd21952cb0d80087b6692477dd97e0a00dfb5faafe2076a76aad8c740
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 25, 2026.
Transparency logRelease files / agentmind_sdk-0.1.1-py3-none-any.whl
| Download URL | agentmind_sdk-0.1.1-py3-none-any.whl |
|---|---|
| Size | 7.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d982c33f08775627598b26b708b71e426bda1075cec813e1babbd957fbf4085d
|
|
BLAKE2b-256 checksum How to use checksums |
f808e635a538334a7624a6d9428b3d39ed40440c33c162ff3dc74141a3fd6c04
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 25, 2026.
Transparency logSecurity for agentmind-sdk 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for agentmind_sdk-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 25, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.